Large scale field-phenotyping approaches have the potential to solve important questions about the relationship of plant genotype to plant phenotype. Computational approaches to measuring the phenotype (the observable plant features) are required to address the problem at a large scale, but machine learning approaches to extract phenotypes from sensor data have been hampered by limited access to (a) sufficiently large, organized multi-sensor datasets, (b) field trials that have a large scale and significant number of genotypes, (c) full genetic sequencing of those phenotypes, and (d) datasets sufficiently organized so that algorithm centered researchers can directly address the real biological problems. To address this, we present SGxP, a novel benchmark dataset from a large-scale field trial consisting of the complete genotype of over 300 sorghum varieties, and time sequences of imagery from several field plots growing each variety, taken with RGB and laser 3D scanner imaging. To lower the barrier to entry and facilitate further developments, we provide a set of well organized, multi-sensor imagery and corresponding genomic data. We implement baseline deep learning based phenotyping approaches to create baseline results for individual sensors and multi-sensor fusion for detecting genetic mutations with known impacts. We also provide and support an open-ended challenge by identifying thousands of genetic mutations whose phenotypic impacts are currently unknown. A web interface for machine learning researchers and practitioners to share approaches, visualizations and hypotheses supports engagement with plant biologists to further the understanding of the sorghum genotype x phenotype relationship. The full dataset, leaderboard (including baseline results) and discussion forums can be found at http://sorghumsnpbenchmark.com.

Testing marine robotics systems in controlled environments before field tests is challenging, especially when acoustic-based sensors and control surfaces only function properly underwater. Deploying robots in indoor tanks and pools often faces space constraints that complicate testing of control, navigation, and perception algorithms at scale. Recent developments of high-fidelity underwater simulation tools have the potential to address these problems. We demonstrate the utility of the recently released HoloOcean 2.0 simulator with improved dynamics for torpedo AUV vehicles and a new ROS 2 interface. We have successfully demonstrated a Hardware-in-the-Loop (HIL) and Software-in-the-Loop (SIL) setup for testing and evaluating a CougUV torpedo autonomous underwater vehicle (AUV) that was built and developed in our lab. With this HIL and SIL setup, simulations are run in HoloOcean using a ROS 2 bridge such that simulated sensor data is sent to the CougUV (mimicking sensor drivers) and control surface commands are sent back to the simulation, where vehicle dynamics and sensor data are calculated. We compare our simulated results to real-world field trial results.

Many incarcerated individuals face significant and complex challenges, including mental illness, substance dependence, and homelessness, yet jails and prisons are often poorly equipped to address these needs. With little support from the existing criminal justice system, these needs can remain untreated and worsen, often leading to further offenses and a cycle of incarceration with adverse outcomes both for the individual and for public safety, with particularly large impacts on communities of color that continue to widen the already extensive racial disparities in criminal justice outcomes. Responding to these failures, a growing number of criminal justice stakeholders are seeking to break this cycle through innovative approaches such as community-driven and alternative approaches to policing, mentoring, community building, restorative justice, pretrial diversion, holistic defense, and social service connections. Here we report on a collaboration between Johnson County, Kansas, and Carnegie Mellon University to perform targeted, proactive mental health outreach in an effort to reduce reincarceration rates. This paper describes the data used, our predictive modeling approach and results, as well as the design and analysis of a field trial conducted to confirm our model's predictive power, evaluate the impact of this targeted outreach, and understand at what level of reincarceration risk outreach might be most effective. Through this trial, we find that our model is highly predictive of new jail bookings, with more than half of individuals in the trial's highest-risk group returning to jail in the following year. Outreach was most effective among these highest-risk individuals, with impacts on mental health utilization, EMS dispatches, and criminal justice involvement.

Large scale field-phenotyping approaches have the potential to solve important questions about the relationship of plant genotype to plant phenotype. Computational approaches to measuring the phenotype (the observable plant features) are required to address the problem at a large scale, but machine learning approaches to extract phenotypes from sensor data have been hampered by limited access to (a) sufficiently large, organized multi-sensor datasets, (b) field trials that have a large scale and significant number of genotypes, (c) full genetic sequencing of those phenotypes, and (d) datasets sufficiently organized so that algorithm centered researchers can directly address the real biological problems. To address this, we present SGxP, a novel benchmark dataset from a large-scale field trial consisting of the complete genotype of over 300 sorghum varieties, and time sequences of imagery from several field plots growing each variety, taken with RGB and laser 3D scanner imaging. To lower the barrier to entry and facilitate further developments, we provide a set of well organized, multi-sensor imagery and corresponding genomic data. We implement baseline deep learning based phenotyping approaches to create baseline results for individual sensors and multi-sensor fusion for detecting genetic mutations with known impacts.

The utilization of existing terrestrial infrastructures to provide coverage for aerial users is a potentially low-cost solution. However, the already deployed terrestrial base stations (TBSs) result in weak ground-to-air (G2A) coverage due to the down-tilted antennas. Furthermore, achieving optimal coverage across the entire airspace through antenna adjustment is challenging due to the complex signal coverage requirements in three-dimensional space, especially in the vertical direction. In this paper, we propose a cooperative tri-point (CoTP) model-based method that utilizes cooperative beams to enhance the G2A coverage extension. To utilize existing TBSs for establishing effective cooperation, we prove that the cooperation among three TBSs can ensure G2A coverage with a minimum coverage overlap, and design the CoTP model to analyze the G2A coverage extension. Using the model, a cooperative coverage structure based on Delaunay triangulation is designed to divide triangular prism-shaped subspaces and corresponding TBS cooperation sets. To enable TBSs in the cooperation set to cover different height subspaces while maintaining ground coverage, we design a cooperative beam generation algorithm to maximize the coverage in the triangular prism-shaped airspace. The simulation results and field trials demonstrate that the proposed method can efficiently enhance the G2A coverage extension while guaranteeing ground coverage.

Crop yield prediction typically involves the utilization of either theory-driven process-based crop growth models, which have proven to be difficult to calibrate for local conditions, or data-driven machine learning methods, which are known to require large datasets. In this work we investigate potato yield prediction using a hybrid meta-modeling approach. A crop growth model is employed to generate synthetic data for (pre)training a convolutional neural net, which is then fine-tuned with observational data. When applied in silico, our meta-modeling approach yields better predictions than a baseline comprising a purely data-driven approach. When tested on real-world data from field trials (n=303) and commercial fields (n=77), the meta-modeling approach yields competitive results with respect to the crop growth model. In the latter set, however, both models perform worse than a simple linear regression with a hand-picked feature set and dedicated preprocessing designed by domain experts. Our findings indicate the potential of meta-modeling for accurate crop yield prediction; however, further advancements and validation using extensive real-world datasets is recommended to solidify its practical effectiveness.

Gene drive organisms (GDOs), whose genomes have been genetically engineered to spread a desired allele through a population, have the potential to transform the way societies address a wide range of daunting public health and environmental challenges. The development, testing, and release of GDOs, however, are complex and often controversial. A key challenge is to clarify the appropriate roles of developers and others actively engaged in work with GDOs in decision-making processes, and, in particular, how to establish partnerships with relevant authorities and other stakeholders. Several members of the gene drive community previously proposed safeguards for laboratory experiments with GDOs ([ 1 ][1]) that, in the absence of national or international guidelines, were considered essential for responsible laboratory work to proceed. Now, with GDO development advancing in laboratories ([ 2 ][2]–[ 5 ][3]), we envision similar safeguards for the potential next step: ecologically and/or genetically confined field trials to further assess the performance of GDOs. A GDO's propensity to spread necessitates well-developed criteria for field trials to assess its potential impacts ([ 6 ][4]). We, as a multidisciplinary group of GDO developers, ecologists, conservation biologists, and experts in social science, ethics, and policy, outline commitments below that we deem critical for responsible conduct of a field trial and to ensure that these technologies, if they are introduced, serve the public interest. ![Figure][5] Characteristics and examples of gene drive organisms Two broad types of engineered approaches exist to modify populations; one requires gene drive and the other relies on non-drive technologies. Multiple examples of these types of systems exist, which can have varied temporal dynamics, including Self-Propagating (with a low threshold; predicted to spread from a GDO release that represents a small percentage of the target population), Majority Wins (with a high threshold; predicted to spread into a population only when the transgene is present in >50% of the target population), and Self-Limiting (temporally limited; can only spread or persist in a population for a short period). These systems can fall under two broad categories: Nonlocalized (predicted, on the basis of a lack of genetic/molecular confinement, to spread beyond boundaries) and Localized (predicted, on the basis of genetic/molecular confinement, to spread only within a localized population). A broad array of GDOs are in development, including those that are geographically localized, nonlocalized, temporally self-limiting, and self-propagating (see the first table). CRISPR/Cas9-based editing has expanded not only the types of GDOs that are possible ([ 2 ][2]–[ 5 ][3]) but also the societal challenges they may help to solve. In particular, major threats to human health may be eliminated by reducing the viability of and/or inducing resistance to pathogens in mosquitoes such as Aedes spp. (major vectors of dengue, chikungunya, and Zika viruses) and Anopheles spp. (major vectors of malaria parasites), or in white-footed mice (carriers of the Lyme disease bacterium). GDOs for suppression of pest populations could also contribute greatly to biodiversity conservation, agricultural productivity, and human and animal well-being. The core commitments presented here (see the second table) are intended to address field trials of either localized GDOs (i.e., GDOs that are genetically or molecularly confined so that they will not spread indefinitely) or nonlocalized GDOs in ecologically isolated locations (e.g., limited-access islands located beyond GDO dispersal capacity, or targeting of a private allele that exists only in an isolated population). Although determinations of whether a GDO is sufficiently confined and who should make these decisions will need to be considered for each GDO and field trial site, introductions of nonlocalized GDOs into sites that are not ecologically isolated would be beyond the scope of these guidelines. We also recognize that these commitments are not enforceable in a regulatory sense; even so, we pledge to apply these commitments to our own practices, recognizing the inherent complexity of this work and our intent to contribute to a fair and ethical culture of gene drive research. These commitments are congruent with guiding principles adopted by several organizations with interests in GDO research ([ 6 ][4]–[ 8 ][6]). We extend these principles specifically to decisions on whether and how to conduct GDO field trials, which will require new and expanding collaborations. To become a signatory to these guiding principles, please visit [www.geneconvenevi.org/supporters-of-the-core-commitments-for-field-trials/][7]. Although field trials of GDOs ultimately will depend on public policy decisions, those engaged in GDO work can play critical roles in support of these decisions by generating evidence and developing evaluation strategies in fair and effective partnerships with relevant authorities and other stakeholders. That the authors of this paper are based largely in high-income countries reflects the current reality that GDO development is occurring primarily in such countries. However, fair partnership with counterparts and communities in low- and middle-income countries where many GDOs have the highest potential for positive impact underlies each of our commitments, as does recognition of the need for capacity-building and global cooperation. Fair partnership among GDO developers, communities where GDOs may be released, regulators (government officials charged with making decisions about whether and how GDOs can be tested locally, even when the regulatory pathway for GDOs may not yet be fully defined), and stakeholders and other experts ([ 6 ][4]) is critical and will require substantial time and resources ([ 9 ][8]). These stakeholders will be engaged in all stages of trial preparation ([ 10 ][9], [ 11 ][10]) and are integral to partners' understanding of existing and required scientific and regulatory capacities of each partner community or country and its political and cultural context. In addition, field site characteristics—such as disease incidence or pest exposure, vector or pest species distributions, and target population genetic background, ecology, and connectivity to surrounding populations—will require input from various stakeholders. This engagement will help to identify the best forms for multidirectional communication and learning, appropriate processes for obtaining government authorization and determining community-level agreement, and meaningful methods to ensure accountability among partners. GDO teams and local and national partners will co-define and collect baseline data needed for each trial, and will prepare an early-response team to address observations in trial-relevant measures. A media communication plan and platform for rapid dissemination of data and interim analyses to field site partners, nongovernmental organizations, and globally interested parties (e.g., open-access journals) should be considered. Plans to provide information on progress and adjustments in the trial, including changes in the release strategy or discontinuation of the study, will be determined in partnership with trial-site community members and government authorities. Transparency about funding, as well as coordination among members of more than one potential release site, is encouraged. In addition, we will work toward a global public registry for communities and laboratories intending to develop GDO applications. This presents challenges in design, implementation, and enforcement of such a registry, including the need to respect the amount of information disclosed. We commit to both these principles of openness and working to establish the tools and methods needed to facilitate fair partnership and transparency. We believe that this work will support project partnerships broadly but should be considered essential for GDO trials. Evidence of laboratory efficacy will be demonstrated prior to a GDO release ([ 12 ][11]). A draft target product profile (TPP), or similar format, detailing acceptable performance parameters and characteristics of the GDO should be prepared by the developer in consultation with regulators [e.g., ([ 13 ][12])]. Evidence of efficacy in the laboratory should include fitness of GDOs, effective release thresholds, stability (i.e., driving capacity maintained over generations), reduction in ability to transmit locally circulating pathogens, and breeding trials with wild strains, as applicable. Results of laboratory cage experiments will help to identify additional data needs. Guidelines proposed in 2015 addressed important biosecurity considerations for laboratory-based GDO research (e.g., laboratory gene drive experiments should use at least two stringent confinement strategies) ([ 1 ][1]). With our expectation that these considerations will already have been addressed before moving toward field testing, we focus here specifically on safety considerations for field testing. Tests of product safety should be conducted prior to, during, and after the release of GDOs, given that natural selection will function during each stage. Recognizing that no action or inaction can be entirely risk-free, required safety levels will be jointly defined with partners, neighboring communities, and regulatory institutions. For example, GDOs' potential to damage or alter closely related or otherwise key species should be examined. Results of experiments assessing both efficacy and safety should be made publicly available within a reasonable time frame. We commit to co-defining safety with trial partners and to openly sharing data on efficacy and safety of a GDO. At a minimum, conducting GDO field trials requires adherence to existing, and often evolving, national (or, in some cases, subnational) regulations and regional and international agreements. Developers will submit required analyses (variously known as risk, safety, and/or environmental assessments) to regulators and respond to their requests, recognizing that regulatory pathways may still be in development. Trial protocols will be reviewed for approval by local ethics boards, institutional review boards, and/or animal care and use committees. Regulators may also require protections of communities where GDOs are released, such as maintaining existing control methods or instituting these methods as a backup to GDOs, and these protections (e.g., use of insecticides or pesticides) should be incorporated into trial design. We believe risk assessment for GDO field trials should include two methodological innovations. First, new methodologies are needed to assess potential social, epidemiological, and ecological benefits and their distribution. Second, we aspire to broaden risk/benefit assessment and make it more inclusive than traditional assessments that rely on expert-defined health and environmental risks, and to explicitly consider issues that may be harder to measure, such as justice. A Procedurally Robust Risk Assessment Framework ([ 14 ][13]) is one model for expanding assessments to include risks of relevance to the social, cultural, and political context. We recognize the value of integrating indigenous and other types of local expert knowledge ([ 15 ][14]), examining socioeconomic risks, and encompassing risks and benefits of introducing or not introducing GDOs in these assessments. ![Figure][5] Core commitments for field trials of gene drive organisms GDO developers should engage and partner with communities, regulators, evolutionary biologists, ecologists, and social scientists to prepare and participate in surveillance for effectiveness and safety, and to monitor unintended consequences before, during, and after release, with accountability to various partners delineated before a field trial. Measures of GDO success will be defined before release and may include evidence of continuing biological function (e.g., prevalence of the transgene in the target population), evidence of elimination of the target population, and evidence of epidemiological, evolutionary, or ecological impacts related to a pathogen or pest. Monitoring systems will be co-designed for early detection of, for example, inadvertent introgression of the transgene into neighboring populations of the target organism or select nontarget species. They will include collection of genetic and/or genomic data of target species prior to release to be compared with post-release populations, so as to understand gene flow and genetic diversity and to characterize potential resistance alleles. Ecological studies are also critical to understanding breeding behavior and other key parameters that may affect field trial protocols. Early all-season modeling of releases at the trial site will help to inform data collection goals, including the geographic and temporal scope of collections, with a buffer zone around the immediate release site depending on the biological characteristics (e.g., dispersal range) of the target species and ecological isolation of the trial site. The length of time needed to demonstrate efficacy and safety of the GDO for wider use will be established at the beginning of the trial, aided by mathematical models. Considerations will include data needed for possible geographic scale-up. Monitoring during field trials will initially include rates of gene drive persistence and spread and will later inform epidemiological or ecological impacts. For trials with epidemiological endpoints, sufficient clinical capacity should be established early in trial design to assess changes in disease incidence. Plans for risk management—in the event of undesired escape of a transgene to neighboring communities or nontarget species; development of resistance in vector, pest, or pathogen; or unintended effects that persist in the population—will depend on the drive construct used and on input from communities, ecologists/scientists, and regulators. Before trial initiation, triggers and risk management strategies will be clearly defined. Capacity for rapid community-wide use of a chosen vector/pest countermeasure should be established, including stocking of chemical control agents (e.g., pesticides) and personnel capacity needed for implementation. The need for social remediation (i.e., responsiveness to social harm/disruption) should be addressed in the risk management plan. Use of countermeasures such as self-limiting systems (see the first table) or drive removal technologies may be considered, with these systems made available and laboratory-tested, with similar framework and rigor, before the trial begins. By presenting our commitments for field trials of GDOs, we aim to prepare for potential field trials that are scientifically, politically, and socially robust, publicly accountable, and widely transparent. Our intent is to contribute to public policy decisions on whether and how to proceed with GDOs, based on evaluations conducted in fair and effective partnerships with relevant authorities and other stakeholders. We recognize our responsibility to work openly; we acknowledge that many innovations beyond those in the laboratory are still needed; and we welcome others, including a broad array of stakeholders in partner countries, to join us in conversation about appropriate governance of this technology and to advance together equitably, safely, and responsibly. [science.sciencemag.org/content/370/6523/1417/suppl/DC1][15] 1. [↵][16]1. O. S. Akbari et al ., Science 349, 927 (2015). [OpenUrl][17][Abstract/FREE Full Text][18] 2. [↵][19]1. H. A. Grunwald et al ., Nature 566, 105 (2019). [OpenUrl][20] 3. 1. V. M. Gantz et al ., Proc. Natl. Acad. Sci. U.S.A. 112, E6736 (2015). [OpenUrl][21][Abstract/FREE Full Text][22] 4. 1. M. Li et al ., Elife 9, e51701 (2020). [OpenUrl][23] 5. [↵][24]1. A. Simoni et al ., Nat. Biotechnol. 38, 1054 (2020). [OpenUrl][25] 6. [↵][26]National Academies of Sciences, Engineering, and Medicine, Gene Drives on the Horizon: Advancing Science, Navigating Uncertainty, and Aligning Research with Public Values (National Academies Press, 2016). 7. 1. C. Emerson, 2. S. James, 3. K. Littler, 4. F. Randazzo , Science 358, 1135 (2017). [OpenUrl][27][Abstract/FREE Full Text][28] 8. [↵][29]1. S. James et al ., Am. J. Trop. Med. Hyg. 98 (suppl. 6), 1 (2018). [OpenUrl][30][CrossRef][31] 9. [↵][32]1. D. Thizy et al ., PLOS Negl. Trop. Dis. 13, e0007286 (2019). [OpenUrl][33] 10. [↵][34]1. D. R. George, 2. T. Kuiken, 3. J. A. Delborne , Proc. R. Soc. B 286, 20191484 (2019). [OpenUrl][35] 11. [↵][36]1. Z. Adelman et al ., Nat. Biotechnol. 35, 716 (2017). [OpenUrl][37][CrossRef][38] 12. [↵][39]1. K. A. Oye et al ., Science 345, 626 (2014). [OpenUrl][40][Abstract/FREE Full Text][41] 13. [↵][42]1. R. Carballar-Lejarazú, 2. A. A. James , Pathog. Glob. Health 111, 424 (2017). [OpenUrl][43][CrossRef][44][PubMed][45] 14. [↵][46]1. J. Kuzma , Regul. Govern. 10.1111/rego.12245 (2019). 15. [↵][47]1. R. Taitingfong , Hum. Biol. 91, 1 (2019). [OpenUrl][48] Acknowledgments: The findings and conclusions in this article are those of the authors and do not necessarily represent the views of the U.S. Fish and Wildlife Service, U.S. Department of Agriculture, DARPA, or other U.S. government organization determination or policy. For additional disclosures, see the supplementary materials. [1]: #ref-1 [2]: #ref-2 [3]: #ref-5 [4]: #ref-6 [5]: pending:yes [6]: #ref-8 [7]: http://www.geneconvenevi.org/supporters-of-the-core-commitments-for-field-trials/ [8]: #ref-9 [9]: #ref-10 [10]: #ref-11 [11]: #ref-12 [12]: #ref-13 [13]: #ref-14 [14]: #ref-15 [15]: http://science.sciencemag.org/content/370/6523/1417/suppl/DC1 [16]: #xref-ref-1-1 "View reference 1 in text" [17]: {openurl}?query=rft.jtitle%253DScience%26rft_id%253Dinfo%253Adoi%252F10.1126%252Fscience.aac7932%26rft_id%253Dinfo%253Apmid%252F26229113%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [18]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6Mzoic2NpIjtzOjU6InJlc2lkIjtzOjEyOiIzNDkvNjI1MS85MjciO3M6NDoiYXRvbSI7czoyMzoiL3NjaS8zNzAvNjUyMy8xNDE3LmF0b20iO31zOjg6ImZyYWdtZW50IjtzOjA6IiI7fQ== [19]: #xref-ref-2-1 "View reference 2 in text" [20]: {openurl}?query=rft.jtitle%253DNature%26rft.volume%253D566%26rft.spage%253D105%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [21]: {openurl}?query=rft.jtitle%253DProc.%2BNatl.%2BAcad.%2BSci.%2BU.S.A.%26rft_id%253Dinfo%253Adoi%252F10.1073%252Fpnas.1521077112%26rft_id%253Dinfo%253Apmid%252F26598698%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [22]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6NDoicG5hcyI7czo1OiJyZXNpZCI7czoxMjoiMTEyLzQ5L0U2NzM2IjtzOjQ6ImF0b20iO3M6MjM6Ii9zY2kvMzcwLzY1MjMvMTQxNy5hdG9tIjt9czo4OiJmcmFnbWVudCI7czowOiIiO30= [23]: {openurl}?query=rft.jtitle%253DElife%26rft.volume%253D9%26rft.spage%253De51701%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [24]: #xref-ref-5-1 "View reference 5 in text" [25]: {openurl}?query=rft.jtitle%253DNat.%2BBiotechnol.%26rft.volume%253D38%26rft.spage%253D1054%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [26]: #xref-ref-6-1 "View reference 6 in text" [27]: {openurl}?query=rft.jtitle%253DScience%26rft.stitle%253DScience%26rft.aulast%253DEmerson%26rft.auinit1%253DC.%26rft.volume%253D358%26rft.issue%253D6367%26rft.spage%253D1135%26rft.epage%253D1136%26rft.atitle%253DPrinciples%2Bfor%2Bgene%2Bdrive%2Bresearch%26rft_id%253Dinfo%253Adoi%252F10.1126%252Fscience.aap9026%26rft_id%253Dinfo%253Apmid%252F29191896%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [28]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6Mzoic2NpIjtzOjU6InJlc2lkIjtzOjEzOiIzNTgvNjM2Ny8xMTM1IjtzOjQ6ImF0b20iO3M6MjM6Ii9zY2kvMzcwLzY1MjMvMTQxNy5hdG9tIjt9czo4OiJmcmFnbWVudCI7czowOiIiO30= [29]: #xref-ref-8-1 "View reference 8 in text" [30]: {openurl}?query=rft.jtitle%253DAm.%2BJ.%2BTrop.%2BMed.%2BHyg.%26rft.volume%253D98%26rft.spage%253D1%26rft_id%253Dinfo%253Adoi%252F10.4269%252Fajtmh.18-0083%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [31]: /lookup/external-ref?access_num=10.4269/ajtmh.18-0083&link_type=DOI [32]: #xref-ref-9-1 "View reference 9 in text" [33]: {openurl}?query=rft.jtitle%253DPLOS%2BNegl.%2BTrop.%2BDis.%26rft.volume%253D13%26rft.spage%253De0007286%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [34]: #xref-ref-10-1 "View reference 10 in text" [35]: {openurl}?query=rft.jtitle%253DProc.%2BR.%2BSoc.%2BB%26rft.volume%253D286%26rft.spage%253D20191484%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [36]: #xref-ref-11-1 "View reference 11 in text" [37]: {openurl}?query=rft.jtitle%253DNat.%2BBiotechnol.%26rft.volume%253D35%26rft.spage%253D716%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fnbt.3926%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [38]: /lookup/external-ref?access_num=10.1038/nbt.3926&link_type=DOI [39]: #xref-ref-12-1 "View reference 12 in text" [40]: {openurl}?query=rft.jtitle%253DScience%26rft_id%253Dinfo%253Adoi%252F10.1126%252Fscience.1254287%26rft_id%253Dinfo%253Apmid%252F25035410%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [41]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6Mzoic2NpIjtzOjU6InJlc2lkIjtzOjEyOiIzNDUvNjE5Ny82MjYiO3M6NDoiYXRvbSI7czoyMzoiL3NjaS8zNzAvNjUyMy8xNDE3LmF0b20iO31zOjg6ImZyYWdtZW50IjtzOjA6IiI7fQ== [42]: #xref-ref-13-1 "View reference 13 in text" [43]: {openurl}?query=rft.jtitle%253DPathog.%2BGlob.%2BHealth%26rft.volume%253D111%26rft.spage%253D424%26rft_id%253Dinfo%253Adoi%252F10.1080%252F20477724.2018.1427192%26rft_id%253Dinfo%253Apmid%252F29385893%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [44]: /lookup/external-ref?access_num=10.1080/20477724.2018.1427192&link_type=DOI [45]: /lookup/external-ref?access_num=29385893&link_type=MED&atom=%2Fsci%2F370%2F6523%2F1417.atom [46]: #xref-ref-14-1 "View reference 14 in text" [47]: #xref-ref-15-1 "View reference 15 in text" [48]: {openurl}?query=rft.jtitle%253DHum.%2BBiol.%26rft.volume%253D91%26rft.spage%253D1%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx

The International Research Institute of Disaster Science at Tohoku University, Earthquake Research Institute at the University of Tokyo, the City of Kawasaki, and Fujitsu Limited have today announced that they will conduct a field trial of AI technology for supporting tsunami evacuations in Kawasaki City on Sunday, November 17th. The four parties have been promoting their Joint Project Aiming for Tsunami Disaster Risk Reduction Using ICT in the Kawasaki Coastal Area since November 2017. The upcoming demonstration will be conducted as a continuation of this project, which most recently included a tsunami evacuation drill conducted with residents of Kawasaki in December 2018. In the Great East Japan Earthquake on March 11, 2011, overconfidence in existing safety protocols and disaster countermeasures, in combination with insufficient communication of disaster information, partly contributed to substantial delays in evacuation. In some cases, this tragically meant that some residents did not realize that a tsunami would strike their location until it was too late, leaving them unprepared to evacuate.

Quivering and hesitant, like a spoon-wielding toddler trying to eat soup without spilling it, the world's first raspberry-picking robot is attempting to harvest one of the fruits. After sizing it up for an age, the robot plucks the fruit with its gripping arm and gingerly deposits it into a waiting punnet. The whole process takes about a minute for a single berry. It seems like heavy going for a robot that cost £700,000 to develop but, if all goes to plan, this is the future of fruit-picking. Each robot will be able to pick more than 25,000 raspberries a day, outpacing human workers who manage about 15,000 in an eight-hour shift, according to Fieldwork Robotics, a spinout from the University of Plymouth.

A Teesside tech firm is gearing up for huge growth as it prepares to lead the rise of the robots with the launch of an artificial intelligence system. Stokesley-based Applied Scientific Technologies is predicting a 10-fold increase in turnover to £4m within two years on the back of the AI system its directors say is at the "the cutting edge of cutting edge". The firm is currently preparing field trials that will see its robotic automated systems go into full production within months. Directors Jamie Marsay, Garry Lofthouse and Lee Raywood are targeting sales of 50 a year of the innovation, which is patent-pending, by 2020. Applied Scientific Technologies (AST) – winner of the Innovation Award at the North East Business Awards 2018 – only launched in May 2017 and already has a raft of blue chip firms as clients, with many more banging at the door for a robotic scientist its creators call The Hyve.